VI

Viloet Eclipse 2x12B v0.2 MINI Reasoning

ViloetGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters21.1B
Context1000K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

Viloet Eclipse 2x12B v0.2 MINI Reasoning needs about 14.7 GB of memory at Q4_K_M (a 12.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 23 quants, from 4.8 GB (IQ1_S) to 17.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

21.1B parameter Viloet Eclipse 2x12B v0.2 MINI Reasoning model

Viloet Eclipse 2x12B v0.2 MINI Reasoning is a 21.1B parameter llama architecture model. It is a mixture of experts trained with a 1,024,000 token context. The model focuses on reasoning and roleplay tasks.

Good at

  • Reasoning
  • Roleplay
  • Multi‑expert inference

Limits

  • Large context length requires high VRAM
  • No vision support
  • License not specified

Best for

  • Complex reasoning tasks
  • Interactive roleplay scenarios
  • Fine‑tuned expert inference

Who it’s for. Developers and researchers needing a large, multi‑expert llama model for reasoning and roleplay. Suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.8 GB 6.6 GB
Fits Get file →
IQ1_M5.2 GB 7.0 GB
Fits Get file →
IQ2_XXS5.9 GB 7.7 GB
Tight Get file →
IQ2_XS6.5 GB 8.3 GB
Too big Get file →
IQ2_S6.7 GB 8.6 GB
Too big Get file →
IQ2_M7.3 GB 9.1 GB
Too big Get file →
Q2_K_S7.5 GB 9.3 GB
Too big Get file →
Q2_K8.0 GB 9.8 GB
Too big Get file →
IQ3_XXS8.3 GB 10.2 GB
Too big Get file →
IQ3_XS8.9 GB 10.7 GB
Too big Get file →
Q3_K_S9.3 GB 11.2 GB
Too big Get file →
IQ3_S9.3 GB 11.2 GB
Too big Get file →
IQ3_M9.6 GB 11.4 GB
Too big Get file →
Q3_K_M10.3 GB 12.1 GB
Too big Get file →
Q3_K_L11.1 GB 12.9 GB
Too big Get file →
IQ4_XS11.4 GB 13.3 GB
Too big Get file →
Q4_012.1 GB 13.9 GB
Too big Get file →
Q4_K_S12.1 GB 14.0 GB
Too big Get file →
Q4_K_M12.8 GB 14.7 GB
Too big Get file →
Q4_113.3 GB 15.1 GB
Too big Get file →
Q5_K_S14.6 GB 16.4 GB
Too big Get file →
Q5_K_M15.0 GB 16.8 GB
Too big Get file →
Q6_K17.3 GB 19.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.77 GB, 6.6 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (6.48 GB, 8.3 GB memory) or Q2_K (7.98 GB, 9.8 GB memory). For 16 GB VRAM, Q3_K_M (10.28 GB, 12.1 GB memory) or Q4_K_M (12.81 GB, 14.7 GB memory). Estimates are approximate.

What GPU do you need for Viloet Eclipse 2x12B v0.2 MINI Reasoning?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ2_XXS (5.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_M (9.6 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (13.3 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.3 GB file, about 19.1 GB in use).

Which Viloet Eclipse 2x12B v0.2 MINI Reasoning quant should you choose?

Q4_K_M is the usual starting point for Viloet Eclipse 2x12B v0.2 MINI Reasoning: it balances file size and quality well. Here it is a 12.8 GB file.

If memory is tight, the smallest file is IQ1_S at 4.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters21.1B (approximate, mixture of experts)
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Frequently asked questions about Viloet Eclipse 2x12B v0.2 MINI Reasoning

How much VRAM does Viloet Eclipse 2x12B v0.2 MINI Reasoning need?

About 14.7 GB at Q4_K_M with an 8K context window. That is the 12.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Viloet Eclipse 2x12B v0.2 MINI Reasoning on an 8 GB GPU?

Yes, with IQ2_XXS: the 5.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Viloet Eclipse 2x12B v0.2 MINI Reasoning GGUF?

It depends on the quant: IQ1_S is 4.8 GB, IQ1_M is 5.2 GB, IQ2_XXS is 5.9 GB, IQ2_XS is 6.5 GB, IQ2_S is 6.7 GB, IQ2_M is 7.3 GB and 17 more.

What context length does Viloet Eclipse 2x12B v0.2 MINI Reasoning support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Viloet Eclipse 2x12B v0.2 MINI Reasoning GGUF?

The files are on Hugging Face in the mradermacher/Viloet-Eclipse-2x12B-v0.2-MINI-Reasoning-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, using the IQ1_S quant (4.77 GB file, ~6.6 GB memory at 8 k context).

Does this model support vision tasks?

No, the model has no vision capability.

What is the maximum context length?

The model was trained with a 1,024,000 token context.

Other GGUFs of Viloet-Eclipse-2x12B-v0.2-MINI-Reasoning

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Viloet models

All Viloet →

Other medium models

All medium models →